Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 162 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0849. Min Range: -9.0849
Max Act: 9.0849. Min Act: -0.1700
Data Index: 8446258 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.3974. Min Act: -0.1700
Data Index: 2463494 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.3349. Min Act: -0.1700
Data Index: 8359544 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.0224. Min Act: -0.1700
Data Index: 817113 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.0224. Min Act: -0.1700
Data Index: 6719430 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.0224. Min Act: -0.1700
Data Index: 5237068 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.0224. Min Act: -0.1700
Data Index: 1461344 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0849. Min Range: -9.0849
Max Act: 7.9599. Min Act: -0.1700
Data Index: 1088661 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0849. Min Range: -9.0849
Max Act: 7.9599. Min Act: -0.1700
Data Index: 5690988 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0849. Min Range: -9.0849
Max Act: 7.9599. Min Act: -0.1700
Data Index: 4358525 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0849. Min Range: -9.0849
Max Act: 8.0224. Min Act: -0.1700
Data Index: 7573654 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0849. Min Range: -9.0849
Max Act: 7.8974. Min Act: -0.1700
Data Index: 3430310 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0849. Min Range: -9.0849
Max Act: 7.8974. Min Act: -0.1700
Data Index: 3251990 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0849. Min Range: -9.0849
Max Act: 7.8974. Min Act: -0.1700
Data Index: 544953 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0849. Min Range: -9.0849
Max Act: 7.8661. Min Act: -0.1700
Data Index: 7054284 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0849. Min Range: -9.0849
Max Act: 7.8349. Min Act: -0.1700
Data Index: 5317178 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0849. Min Range: -9.0849
Max Act: 7.8349. Min Act: -0.1700
Data Index: 1518628 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0849. Min Range: -9.0849
Max Act: 7.8349. Min Act: -0.1700
Data Index: 8674027 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0849. Min Range: -9.0849
Max Act: 7.8036. Min Act: -0.1700
Data Index: 6711385 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0849. Min Range: -9.0849
Max Act: 7.8036. Min Act: -0.1700
Data Index: 1312703 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19